Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

By Tiansheng Wen, Yi-Fei Wang, Zequn Zeng, Zhong Peng, Yudi Su, Xin-Yang Liu, Bo Chen, Hongwei Liu, Stefanie Jegelka, Chen-Yu You. 2025

Subfields: Representation & Self-Supervised Learning, Efficiency & Compression

Citations in the corpus

• LLMs Meet Isolation Kernel: Lightweight, Learning-free Binary Embeddings for Fast Retrieval (2026, unknown): “Recently, Wen et al. (2025) proposed CSR, which combines sparse coding with contrastive learning to produce efficient sparse embeddings with minimal performance loss.”
• The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems (2025, unknown): “52% (Figure 3, right).”
• Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval (2026, unknown): “We compare the works above in Table 7.”